@inproceedings{narzary-etal-2022-generating,
title = "Generating Monolingual Dataset for Low Resource Language {B}odo from old books using {G}oogle Keep",
author = "Narzary, Sanjib and
Brahma, Maharaj and
Narzary, Mwnthai and
Muchahary, Gwmsrang and
Singh, Pranav Kumar and
Senapati, Apurbalal and
Nandi, Sukumar and
Som, Bidisha",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.705",
pages = "6563--6570",
abstract = "Bodo is a scheduled Indian language spoken largely by the Bodo community of Assam and other northeastern Indian states. Due to a lack of resources, it is difficult for young languages to communicate more effectively with the rest of the world. This leads to a lack of research in low-resource languages. The creation of a dataset is a tedious and costly process, particularly for languages with no participatory research. This is more visible for languages that are young and have recently adopted standard writing scripts. In this paper, we present a methodology using Google Keep for OCR to generate a monolingual Bodo corpus from different books. In this work, a Bodo text corpus of 192,327 tokens and 32,268 unique tokens is generated using free, accessible, and daily-usable applications. Moreover, some essential characteristics of the Bodo language are discussed that are neglected by Natural Language Progressing (NLP) researchers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="narzary-etal-2022-generating">
<titleInfo>
<title>Generating Monolingual Dataset for Low Resource Language Bodo from old books using Google Keep</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanjib</namePart>
<namePart type="family">Narzary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maharaj</namePart>
<namePart type="family">Brahma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mwnthai</namePart>
<namePart type="family">Narzary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gwmsrang</namePart>
<namePart type="family">Muchahary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apurbalal</namePart>
<namePart type="family">Senapati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sukumar</namePart>
<namePart type="family">Nandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bidisha</namePart>
<namePart type="family">Som</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bodo is a scheduled Indian language spoken largely by the Bodo community of Assam and other northeastern Indian states. Due to a lack of resources, it is difficult for young languages to communicate more effectively with the rest of the world. This leads to a lack of research in low-resource languages. The creation of a dataset is a tedious and costly process, particularly for languages with no participatory research. This is more visible for languages that are young and have recently adopted standard writing scripts. In this paper, we present a methodology using Google Keep for OCR to generate a monolingual Bodo corpus from different books. In this work, a Bodo text corpus of 192,327 tokens and 32,268 unique tokens is generated using free, accessible, and daily-usable applications. Moreover, some essential characteristics of the Bodo language are discussed that are neglected by Natural Language Progressing (NLP) researchers.</abstract>
<identifier type="citekey">narzary-etal-2022-generating</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.705</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6563</start>
<end>6570</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Monolingual Dataset for Low Resource Language Bodo from old books using Google Keep
%A Narzary, Sanjib
%A Brahma, Maharaj
%A Narzary, Mwnthai
%A Muchahary, Gwmsrang
%A Singh, Pranav Kumar
%A Senapati, Apurbalal
%A Nandi, Sukumar
%A Som, Bidisha
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F narzary-etal-2022-generating
%X Bodo is a scheduled Indian language spoken largely by the Bodo community of Assam and other northeastern Indian states. Due to a lack of resources, it is difficult for young languages to communicate more effectively with the rest of the world. This leads to a lack of research in low-resource languages. The creation of a dataset is a tedious and costly process, particularly for languages with no participatory research. This is more visible for languages that are young and have recently adopted standard writing scripts. In this paper, we present a methodology using Google Keep for OCR to generate a monolingual Bodo corpus from different books. In this work, a Bodo text corpus of 192,327 tokens and 32,268 unique tokens is generated using free, accessible, and daily-usable applications. Moreover, some essential characteristics of the Bodo language are discussed that are neglected by Natural Language Progressing (NLP) researchers.
%U https://aclanthology.org/2022.lrec-1.705
%P 6563-6570
Markdown (Informal)
[Generating Monolingual Dataset for Low Resource Language Bodo from old books using Google Keep](https://aclanthology.org/2022.lrec-1.705) (Narzary et al., LREC 2022)
ACL
- Sanjib Narzary, Maharaj Brahma, Mwnthai Narzary, Gwmsrang Muchahary, Pranav Kumar Singh, Apurbalal Senapati, Sukumar Nandi, and Bidisha Som. 2022. Generating Monolingual Dataset for Low Resource Language Bodo from old books using Google Keep. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6563–6570, Marseille, France. European Language Resources Association.